[Issue][ONNX]: Error simplify_reshapes: src/include/migraphx/check_shapes.hpp:221: same_dims: mul: Dimensions do not match
Open
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 333
- Forks
- 150
- Avg merge
- 4d 19h
- Merged PRs (30d)
- 54
Description
Problem Description
See https://github.com/microsoft/onnxruntime/issues/31713 and https://github.com/microsoft/onnxruntime/issues/31607 for context.
This also requires fixes from both https://github.com/microsoft/onnxruntime/pull/31623 and https://github.com/microsoft/onnxruntime/pull/31978 to be applied to the MIGraphX execution provider first.
When loading https://gitlab.collabora.com/gstreamer/onnx-models/-/blob/a8de628ad5a745d3af6ba8c0ee84321605de07e9/models/ssd_mobilenet_v1_coco.onnx or https://huggingface.co/onnxmodelzoo/ssd_mobilenet_v1_12 via the ONNX MIGraphX execution provider, this fails:
$ ./migraphx_sample migraphx onnx-models/models/ssd_mobilenet_v1_coco.onnx
Loading: onnx-models/models/ssd_mobilenet_v1_coco.onnx (provider: migraphx, device: 0)
2026-08-11 11:46:40.219688249 [W:onnxruntime:sample, migraphx_execution_provider.cc:167 MIGraphXExecutionProvider] [MIGraphX EP] MIGraphX ENV Override Variables Set:
2026-08-11 11:46:40.910929074 [W:onnxruntime:, session_state.cc:1387 VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2026-08-11 11:46:40.910958600 [W:onnxruntime:, session_state.cc:1389 VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
Session created successfully.
Input 0: image_tensor:0 shape=[1, 300, 300, 3]
Running inference...
2026-08-11 11:46:42.301283300 [W:onnxruntime:sample, migraphx_execution_provider.cc:1367 compile_program] Model Compile: Begin
2026-08-11 11:46:42.321963 [ERROR] [AMDMIGraphX/src/pass_manager.cpp:176] Error simplify_reshapes: AMDMIGraphX/src/include/migraphx/check_shapes.hpp:221: same_dims: mul: Dimensions do not match
2026-08-11 11:46:42.322002 [ERROR] [AMDMIGraphX/src/pass_manager.cpp:186] Dump: "/tmp/migraphx/simplify_reshapes77780430370983.mxr"
migraphx_program_compile: Error: AMDMIGraphX/src/include/migraphx/check_shapes.hpp:221: same_dims: mul: Dimensions do not match
2026-08-11 11:46:42.381483212 [E:onnxruntime:, sequential_executor.cc:671 ExecuteKernel] Non-zero status code returned while running MGXKernel_graph_tf2onnx_9255412890226604894_0 node. Name:'MIGraphXExecutionProvider_MGXKernel_graph_tf2onnx_9255412890226604894_0_0' Status Message: Failed to call function
terminate called after throwing an instance of 'Ort::Exception'
what(): Non-zero status code returned while running MGXKernel_graph_tf2onnx_9255412890226604894_0 node. Name:'MIGraphXExecutionProvider_MGXKernel_graph_tf2onnx_9255412890226604894_0_0' Status Message: Failed to call function
fish: Job 1, 'ORT_MIGRAPHX_MODEL_CACHE_PATH=(…' terminated by signal SIGABRT (Abort)
From what I understand what happens here is that the graph is correctly parsed but then compilation fails because it ends up with a mul between a scalar and a {1, 300, 300, 3} tensor. There's probably a missing multibroadcast, or it was simplified away wrongly.
Operating System
Fedora F44
CPU
AMD Ryzen 9 7950X
GPU
Other
Other
Radeon AI PRO R9700
ROCm Version
ROCm 6.0.0
Steps to Reproduce
Can be reproduced with migraphx_sample.cc.txt or anything else trying to load that model and actually passing an input tensor to it.
Run with
./migraphx_sample migraphx onnx-models/models/ssd_mobilenet_v1_coco.onnx
Using cpu instead of migraphx makes it work.
(Optional for Linux users) Output of /opt/rocm/bin/rocminfo --support
ROCk module is loaded
=====================
HSA System Attributes
=====================
Runtime Version: 1.21
Runtime Ext Version: 1.30
System Timestamp Freq.: 1000.000000MHz
Sig. Max Wait Duration: 18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count)
Machine Model: LARGE
System Endianness: LITTLE
Mwaitx: ENABLED
XNACK enabled: NO
DMAbuf Support: YES
VMM Support: YES
Fabric Support: NO
==========
HSA Agents
==========
*******
Agent 1
*******
Name: AMD Ryzen 9 7950X 16-Core Processor
Uuid: CPU-XX
Marketing Name: AMD Ryzen 9 7950X 16-Core Processor
Vendor Name: CPU
Feature: None specified
Profile: FULL_PROFILE
Float Round Mode: NEAR
Max Queue Number: 0(0x0)
Queue Min Size: 0(0x0)
Queue Max Size: 0(0x0)
Queue Type: MULTI
Node: 0
Device Type: CPU
Cache Info:
L1: 32768(0x8000) KB
Chip ID: 0(0x0)
ASIC Revision: 0(0x0)
Cacheline Size: 64(0x40)
Max Clock Freq. (MHz): 5883
BDFID: 0
Internal Node ID: 0
Compute Unit: 32
SIMDs per CU: 0
Shader Engines: 0
Shader Arrs. per Eng.: 0
WatchPts on Addr. Ranges:1
Memory Properties:
Features: None
Pool Info:
Pool 1
Segment: GLOBAL; FLAGS: FINE GRAINED
Size: 127352388(0x7973e44) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:4KB
Alloc Alignment: 4KB
Accessible by all: TRUE
Pool 2
Segment: GLOBAL; FLAGS: EXTENDED FINE GRAINED
Size: 127352388(0x7973e44) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:4KB
Alloc Alignment: 4KB
Accessible by all: TRUE
Pool 3
Segment: GLOBAL; FLAGS: KERNARG, FINE GRAINED
Size: 127352388(0x7973e44) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:4KB
Alloc Alignment: 4KB
Accessible by all: TRUE
Pool 4
Segment: GLOBAL; FLAGS: COARSE GRAINED
Size: 127352388(0x7973e44) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:4KB
Alloc Alignment: 4KB
Accessible by all: TRUE
ISA Info:
*******
Agent 2
*******
Name: gfx1201
Uuid: GPU-9fca5606eeb2aa78
Marketing Name: AMD Radeon AI PRO R9700
Vendor Name: AMD
Feature: KERNEL_DISPATCH
Profile: BASE_PROFILE
Float Round Mode: NEAR
Max Queue Number: 128(0x80)
Queue Min Size: 64(0x40)
Queue Max Size: 131072(0x20000)
Queue Type: MULTI
Node: 1
Device Type: GPU
Cache Info:
L1: 32(0x20) KB
L2: 8192(0x2000) KB
L3: 65536(0x10000) KB
Chip ID: 30033(0x7551)
ASIC Revision: 1(0x1)
Cacheline Size: 256(0x100)
Max Clock Freq. (MHz): 2350
BDFID: 768
Internal Node ID: 1
Compute Unit: 64
SIMDs per CU: 2
Shader Engines: 4
Shader Arrs. per Eng.: 2
WatchPts on Addr. Ranges:4
Coherent Host Access: FALSE
Memory Properties:
Features: KERNEL_DISPATCH
Fast F16 Operation: TRUE
Wavefront Size: 32(0x20)
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension:
x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Max Waves Per CU: 32(0x20)
Max Work-item Per CU: 1024(0x400)
Grid Max Size: 2147483647(0x7fffffff)
Grid Max Size per Dimension:
x 2147483647(0x7fffffff)
y 65535(0xffff)
z 65535(0xffff)
Max fbarriers/Workgrp: 32
Packet Processor uCode:: 268
SDMA engine uCode:: 662
IOMMU Support:: None
Pool Info:
Pool 1
Segment: GLOBAL; FLAGS: COARSE GRAINED
Size: 33406976(0x1fdc000) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:2048KB
Alloc Alignment: 4KB
Accessible by all: FALSE
Pool 2
Segment: GROUP
Size: 64(0x40) KB
Allocatable: FALSE
Alloc Granule: 0KB
Alloc Recommended Granule:0KB
Alloc Alignment: 0KB
Accessible by all: FALSE
ISA Info:
ISA 1
Name: amdgcn-amd-amdhsa--gfx1201
Machine Models: HSA_MACHINE_MODEL_LARGE
Profiles: HSA_PROFILE_BASE
Default Rounding Mode: NEAR
Default Rounding Mode: NEAR
Fast f16: TRUE
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension:
x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension:
x 2147483647(0x7fffffff)
y 65535(0xffff)
z 65535(0xffff)
FBarrier Max Size: 32
ISA 2
Name: amdgcn-amd-amdhsa--gfx12-generic
Machine Models: HSA_MACHINE_MODEL_LARGE
Profiles: HSA_PROFILE_BASE
Default Rounding Mode: NEAR
Default Rounding Mode: NEAR
Fast f16: TRUE
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension:
x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension:
x 2147483647(0x7fffffff)
y 65535(0xffff)
z 65535(0xffff)
FBarrier Max Size: 32
*******
Agent 3
*******
Name: gfx1036
Uuid: GPU-XX
Marketing Name: AMD Radeon Graphics
Vendor Name: AMD
Feature: KERNEL_DISPATCH
Profile: BASE_PROFILE
Float Round Mode: NEAR
Max Queue Number: 128(0x80)
Queue Min Size: 64(0x40)
Queue Max Size: 131072(0x20000)
Queue Type: MULTI
Node: 2
Device Type: GPU
Cache Info:
L1: 16(0x10) KB
L2: 256(0x100) KB
Chip ID: 5710(0x164e)
ASIC Revision: 1(0x1)
Cacheline Size: 128(0x80)
Max Clock Freq. (MHz): 2200
BDFID: 5632
Internal Node ID: 2
Compute Unit: 2
SIMDs per CU: 2
Shader Engines: 1
Shader Arrs. per Eng.: 1
WatchPts on Addr. Ranges:4
Coherent Host Access: FALSE
Memory Properties: APU
Features: KERNEL_DISPATCH
Fast F16 Operation: TRUE
Wavefront Size: 32(0x20)
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension:
x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Max Waves Per CU: 32(0x20)
Max Work-item Per CU: 1024(0x400)
Grid Max Size: 2147483647(0x7fffffff)
Grid Max Size per Dimension:
x 2147483647(0x7fffffff)
y 65535(0xffff)
z 65535(0xffff)
Max fbarriers/Workgrp: 32
Packet Processor uCode:: 28
SDMA engine uCode:: 9
IOMMU Support:: None
Pool Info:
Pool 1
Segment: GLOBAL; FLAGS: COARSE GRAINED
Size: 63676192(0x3cb9f20) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:2048KB
Alloc Alignment: 4KB
Accessible by all: FALSE
Pool 2
Segment: GLOBAL; FLAGS: EXTENDED FINE GRAINED
Size: 63676192(0x3cb9f20) KB
Allocatable: TRUE
Alloc Granule: 4KB
Alloc Recommended Granule:2048KB
Alloc Alignment: 4KB
Accessible by all: FALSE
Pool 3
Segment: GROUP
Size: 64(0x40) KB
Allocatable: FALSE
Alloc Granule: 0KB
Alloc Recommended Granule:0KB
Alloc Alignment: 0KB
Accessible by all: FALSE
ISA Info:
ISA 1
Name: amdgcn-amd-amdhsa--gfx1036
Machine Models: HSA_MACHINE_MODEL_LARGE
Profiles: HSA_PROFILE_BASE
Default Rounding Mode: NEAR
Default Rounding Mode: NEAR
Fast f16: TRUE
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension:
x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension:
x 2147483647(0x7fffffff)
y 65535(0xffff)
z 65535(0xffff)
FBarrier Max Size: 32
ISA 2
Name: amdgcn-amd-amdhsa--gfx10-3-generic
Machine Models: HSA_MACHINE_MODEL_LARGE
Profiles: HSA_PROFILE_BASE
Default Rounding Mode: NEAR
Default Rounding Mode: NEAR
Fast f16: TRUE
Workgroup Max Size: 1024(0x400)
Workgroup Max Size per Dimension:
x 1024(0x400)
y 1024(0x400)
z 1024(0x400)
Grid Max Size: 4294967295(0xffffffff)
Grid Max Size per Dimension:
x 2147483647(0x7fffffff)
y 65535(0xffff)
z 65535(0xffff)
FBarrier Max Size: 32
*** Done ***
Additional Information
ROCm version selected above is wrong as it stops at 6.0.0 but we're now at ROCm 7.14. This is with ROCm 7.15.0 (20260803-30774164023) / MIGraphX rocm-7.14 tag and onnxruntime 1.28.0 plus the fixes mentioned above.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with src/include/migraphx/check_shapes.hpp:221 and reproduce the failure using migraphx_sample.cc.txt with ssd_mobilenet_v1_coco.onnx. Review the linked ONNX Runtime issues and pull requests, which must be applied to the MIGraphX execution provider first. Done means the model loads and runs with the MIGraphX provider without the simplify_reshapes dimension-mismatch error.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- backend, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 42/100